English
Related papers

Related papers: KALE Flow: A Relaxed KL Gradient Flow for Probabil…

200 papers

The capability of a novel Kullback-Leibler divergence method is examined herein within the Kalman filter framework to select the input-parameter-state estimation execution with the most plausible results. This identification suffers from…

Signal Processing · Electrical Eng. & Systems 2025-11-05 Marios Impraimakis

Flow Matching has recently gained attention in generative modeling as a simple and flexible alternative to diffusion models. While existing statistical guarantees adapt tools from the analysis of diffusion models, we take a different…

Machine Learning · Statistics 2026-03-18 Lea Kunkel , Mathias Trabs

We introduce a novel nonlinear Kalman filter that utilizes reparametrization gradients. The widely used parametric approximation is based on a jointly Gaussian assumption of the state-space model, which is in turn equivalent to minimizing…

Machine Learning · Computer Science 2023-03-09 San Gultekin , Brendan Kitts , Aaron Flores , John Paisley

Trajectory Inference (TI) seeks to recover latent dynamical processes from snapshot data, where only independent samples from time-indexed marginals are observed. In applications such as single-cell genomics, destructive measurements make…

Machine Learning · Computer Science 2026-04-23 Chao Wang , Luca Nepote , Giulio Franzese , Pietro Michiardi

Wasserstein gradient flows have become a central tool for optimization problems over probability measures. A natural numerical approach is forward-Euler time discretization. We show, however, that even in the simple case where the energy…

Numerical Analysis · Mathematics 2025-10-16 Yewei Xu , Qin Li

We analyze the gradient flow of a potential energy in the space of probability measures when we substitute the optimal transport geometry with a geometry based on Sinkhorn divergences, a debiased version of entropic optimal transport. This…

Analysis of PDEs · Mathematics 2025-11-19 Mathis Hardion , Hugo Lavenant

This paper presents an improved exponential tail bound for Beta distributions, refining a result in [15]. This improvement is achieved by interpreting their bound as a regular Kullback-Leibler (KL) divergence one, while introducing a…

Probability · Mathematics 2025-08-12 Pierre Perrault

Estimating entropy and mutual information consistently is important for many machine learning applications. The Kozachenko-Leonenko (KL) estimator (Kozachenko & Leonenko, 1987) is a widely used nonparametric estimator for the entropy of…

Statistics Theory · Mathematics 2016-07-22 Shashank Singh , Barnabás Póczos

FRAME (Filters, Random fields, And Maximum Entropy) is an energy-based descriptive model that synthesizes visual realism by capturing mutual patterns from structural input signals. The maximum likelihood estimation (MLE) is applied by…

Machine Learning · Computer Science 2019-01-17 Xu Cai , Yang Wu , Guanbin Li , Ziliang Chen , Liang Lin

Knowledge distillation (KD) has been proven to be a simple and effective tool for training compact models. Almost all KD variants for dense prediction tasks align the student and teacher networks' feature maps in the spatial domain,…

Computer Vision and Pattern Recognition · Computer Science 2021-08-30 Changyong Shu , Yifan Liu , Jianfei Gao , Zheng Yan , Chunhua Shen

We consider in this work small random perturbations (of multiplicative noise type) of the gradient flow. We prove that under mild conditions, when the potential function is a Morse function with additional strong saddle condition, the…

Probability · Mathematics 2020-04-29 Jiaojiao Yang , Wenqing Hu , Chris Junchi Li

Langevin diffusion is a commonly used tool for sampling from a given distribution. In this work, we establish that when the target density $p^*$ is such that $\log p^*$ is $L$ smooth and $m$ strongly convex, discrete Langevin diffusion…

Machine Learning · Statistics 2017-11-02 Xiang Cheng , Peter Bartlett

We suggest an iterative approach to computing K-step maximum likelihood estimates (MLE) of the parametric components in semiparametric models based on their profile likelihoods. The higher order convergence rate of K-step MLE mainly depends…

Statistics Theory · Mathematics 2007-08-23 Guang Cheng

Generative flow networks (GFNs) are a class of models for sequential sampling of composite objects, which approximate a target distribution that is defined in terms of an energy function or a reward. GFNs are typically trained using a flow…

Machine Learning · Statistics 2022-10-17 Heiko Zimmermann , Fredrik Lindsten , Jan-Willem van de Meent , Christian A. Naesseth

Coupling arguments are a central tool for bounding the deviation between two stochastic processes, but traditionally have been limited to Wasserstein metrics. In this paper, we apply the shifted composition rule--an information-theoretic…

Statistics Theory · Mathematics 2024-12-25 Jason M. Altschuler , Sinho Chewi

The Fokker-Planck equation can be reformulated as a continuity equation, which naturally suggests using the associated velocity field in particle flow methods. While the resulting probability flow ODE offers appealing properties - such as…

Machine Learning · Statistics 2024-10-28 Ilja Klebanov

It is commonly believed that optimizing the reverse KL divergence results in "mode seeking", while optimizing forward KL results in "mass covering", with the latter being preferred if the goal is to sample from multiple diverse modes. We…

Machine Learning · Computer Science 2025-10-24 Anthony GX-Chen , Jatin Prakash , Jeff Guo , Rob Fergus , Rajesh Ranganath

Discrete diffusion and flow matching models capture complex, non-additive and non-autoregressive structure in high-dimensional objective landscapes through parallel, iterative refinement. However, their implicit generative nature precludes…

Machine Learning · Computer Science 2026-03-03 Yashvir S. Grewal , Daniel M. Steinberg , Thang D. Bui , Cheng Soon Ong , Edwin V. Bonilla

Measure transport underpins several recent algorithms for posterior approximation in the Bayesian context, wherein a transport map is sought to minimise the Kullback--Leibler divergence (KLD) from the posterior to the approximation. The KLD…

Computation · Statistics 2020-10-27 Matthew A. Fisher , Tui Nolan , Matthew M. Graham , Dennis Prangle , Chris J. Oates

Diffusion models have achieved great success in generating high-dimensional samples across various applications. While the theoretical guarantees for continuous-state diffusion models have been extensively studied, the convergence analysis…

Machine Learning · Computer Science 2025-04-15 Zikun Zhang , Zixiang Chen , Quanquan Gu